Synchronizing local compiler cache.

neuronxcc-2.17.194.0+d312836f/0_REGISTRY/0.3.0.dev2/stable-diffusion/stabilityai/sdxl-turbo/68031b89e85788c276aa.json

@@ -0,0 +1,162 @@
+{
+  "_entry_class": "MultiModelCacheEntry",
+  "_model_id": "stabilityai/sdxl-turbo",
+  "_task": null,
+  "text_encoder": {
+    "architectures": [
+      "CLIPTextModel"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "quick_gelu",
+    "hidden_size": 768,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 3072,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.17.194.0+d312836f",
+      "dynamic_batch_size": false,
+      "inline_weights_to_neff": false,
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 77,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 12,
+    "num_hidden_layers": 12,
+    "output_hidden_states": true,
+    "vocab_size": 49408
+  },
+  "text_encoder_2": {
+    "architectures": [
+      "CLIPTextModelWithProjection"
+    ],
+    "attention_dropout": 0.0,
+    "dropout": 0.0,
+    "hidden_act": "gelu",
+    "hidden_size": 1280,
+    "initializer_factor": 1.0,
+    "initializer_range": 0.02,
+    "intermediate_size": 5120,
+    "layer_norm_eps": 1e-05,
+    "max_position_embeddings": 77,
+    "model_type": "clip_text_model",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.17.194.0+d312836f",
+      "dynamic_batch_size": false,
+      "inline_weights_to_neff": false,
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_sequence_length": 77,
+      "task": "feature-extraction",
+      "tensor_parallel_size": 1
+    },
+    "num_attention_heads": 20,
+    "num_hidden_layers": 32,
+    "output_hidden_states": true,
+    "vocab_size": 49408
+  },
+  "unet": {
+    "_class_name": "UNet2DConditionModel",
+    "act_fn": "silu",
+    "addition_embed_type": "text_time",
+    "addition_embed_type_num_heads": 64,
+    "addition_time_embed_dim": 256,
+    "attention_head_dim": [
+      5,
+      10,
+      20
+    ],
+    "attention_type": "default",
+    "block_out_channels": [
+      320,
+      640,
+      1280
+    ],
+    "center_input_sample": false,
+    "class_embed_type": null,
+    "class_embeddings_concat": false,
+    "conv_in_kernel": 3,
+    "conv_out_kernel": 3,
+    "cross_attention_dim": 2048,
+    "cross_attention_norm": null,
+    "down_block_types": [
+      "DownBlock2D",
+      "CrossAttnDownBlock2D",
+      "CrossAttnDownBlock2D"
+    ],
+    "downsample_padding": 1,
+    "dropout": 0.0,
+    "dual_cross_attention": false,
+    "encoder_hid_dim": null,
+    "encoder_hid_dim_type": null,
+    "flip_sin_to_cos": true,
+    "freq_shift": 0,
+    "in_channels": 4,
+    "layers_per_block": 2,
+    "mid_block_only_cross_attention": null,
+    "mid_block_scale_factor": 1,
+    "mid_block_type": "UNetMidBlock2DCrossAttn",
+    "neuron": {
+      "auto_cast": "matmul",
+      "auto_cast_type": "bf16",
+      "compiler_type": "neuronx-cc",
+      "compiler_version": "2.17.194.0+d312836f",
+      "dynamic_batch_size": false,
+      "inline_weights_to_neff": true,
+      "optlevel": "2",
+      "output_attentions": false,
+      "output_hidden_states": false,
+      "static_batch_size": 1,
+      "static_height": 128,
+      "static_num_channels": 4,
+      "static_sequence_length": 77,
+      "static_vae_scale_factor": 8,
+      "static_width": 128,
+      "task": "semantic-segmentation",
+      "tensor_parallel_size": 1
+    },
+    "norm_eps": 1e-05,
+    "norm_num_groups": 32,
+    "num_attention_heads": null,
+    "num_class_embeds": null,
+    "only_cross_attention": false,
+    "out_channels": 4,
+    "projection_class_embeddings_input_dim": 2816,
+    "resnet_out_scale_factor": 1.0,
+    "resnet_skip_time_act": false,
+    "resnet_time_scale_shift": "default",
+    "reverse_transformer_layers_per_block": null,
+    "time_cond_proj_dim": null,
+    "time_embedding_act_fn": null,
+    "time_embedding_dim": null,
+    "time_embedding_type": "positional",
+    "timestep_post_act": null,
+    "transformer_layers_per_block": [
+      1,
+      2,
+      10
+    ],
+    "up_block_types": [
+      "CrossAttnUpBlock2D",
+      "CrossAttnUpBlock2D",
+      "UpBlock2D"
+    ],
+    "upcast_attention": null,
+    "use_linear_projection": true
+  }
+}

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/text_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8d5860bc2a5a81c343244708bc0927d6d64902f6dd7a20b7ad4814eb0e403814
+oid sha256:dbe4ae6e3513d633750f29d2b39a61eebb13926d046866523a0b6ef641ce8b62
 size 495950649

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/text_encoder_2/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79bd13ed7e3479b5634a00fea7d065945c231292ff488c702731c5cf45c9adb4
+oid sha256:1527b20b1dcf83ec8f2ce8814adb8fbcc0ba8c1384336c96df91a66b5cef81e5
 size 2801222123

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/unet/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3d9c6f2d36e7c4c554695ff9dbc0713627fe7a499c741085ccc772dc31b87c39
+oid sha256:b7544c98ca1a96dfb8f640d06593a65ba0042cc6e216228e2dc6dede69a9bb1b
 size 4173421885

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/vae_decoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
-    "latents_std",
     "latents_mean",
-    "shift_factor",
-    "use_post_quant_conv",
+    "mid_block_add_attention",
+    "latents_std",
     "use_quant_conv",
-    "mid_block_add_attention"
+    "use_post_quant_conv",
+    "shift_factor"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/vae_decoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8a2e1a2948fa62c82759cb0560bc790ffa5719bf7687a8bc6d01468a8221669d
+oid sha256:ead414709cd5f8fdacebf41033ecf37f922118fdcf449b746894cd8aed7ea25b
 size 749922867

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/vae_encoder/config.json

@@ -3,12 +3,12 @@
   "_commit_hash": null,
   "_diffusers_version": "0.30.3",
   "_use_default_values": [
-    "latents_std",
     "latents_mean",
-    "shift_factor",
-    "use_post_quant_conv",
+    "mid_block_add_attention",
+    "latents_std",
     "use_quant_conv",
-    "mid_block_add_attention"
+    "use_post_quant_conv",
+    "shift_factor"
   ],
   "act_fn": "silu",
   "block_out_channels": [

neuronxcc-2.17.194.0+d312836f/MODULE_68031b89e85788c276aa/vae_encoder/model.neuron

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:727bc6d6114b3b8f81f4a61bc2b9c03f747e847d80346b0bcc73c29a953be396
+oid sha256:a7e38c98a06ed0b99fa0ec56ea94b06f976ed45e3359c262cbb4d0a96e9111e1
 size 382102067